SurfSense is an open-source desktop application that uses an AI agent to research, transform, and edit documents while keeping their index on the user's machine. It is intended for people working with documents they cannot upload, with a choice of local or remote models and no account required.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MODSetter/SurfSense --skill xlsxgit clone --depth 1 https://github.com/MODSetter/SurfSenseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modsetter/surfsense/xlsx)<a href="https://agentmods.dev/skills/modsetter/surfsense/xlsx"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/xlsx/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modsetter/surfsense/xlsx"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/xlsx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00825 |
| Opus 5.5 | $0.00008 | $0.00330 |
| Sonnet 5.5 | $0.00004 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
xlsx scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XLSX
Create the requested workbook in /workspace with the preinstalled
xlsxwriter and openpyxl packages. Never install or download dependencies.
Use XlsxWriter for new workbooks because it can write explicit formula caches
that verification and the browser grid require.
Authoring rules
- Prefer one clear sheet purpose per worksheet. Name sheets for the user, not
Sheet1/Sheet2, unless the request is a blank template. - Set column widths deliberately. Freeze header rows when tables are scrolled.
- Style headers once (bold, fill, borders) and reuse the style objects. Prefer
number formats (
#,##0.00,0%, dates) over pre-formatted strings. - Write formulas with both the formula string and a computed cached value:
worksheet.write_formula("B2", "=A2*1.1", cell_format, 110). Verification rejects formula cells that lack a cached result, and the in-browser grid shows the cache rather than recalculating. - Also call
workbook.set_calc_mode("auto")(or the equivalent recalculation on open) so Excel/LibreOffice recompute when the file is opened. - Never leave Excel error literals (
#DIV/0!,#REF!,#VALUE!,#N/A, …) as cached results. Fix the formula or the inputs instead. - Keep workbooks under the verification cell ceiling (100 000 cells). Prefer compact tables over giant empty ranges.
- Charts, pivot tables, macros, and VBA are out of scope for this skill. Stick to values, formulas, formats, panes, and multiple sheets.
Revisions
Start an in-place revision with load_artifact_for_revision. Open
primary_path with openpyxl using data_only=False, edit that current
workbook directly, and write the revision to expected_output_path. Preserve
unaffected worksheets, formulas, formatting, panes, validation, links, and
workbook settings. Use markdown_path as textual context, not as a replacement
workbook. Do not use vision to reconstruct workbook contents.
If the workbook contains formulas, saving with openpyxl is not the final
step: run headless LibreOffice on a temporary copy and place the recalculated
XLSX at expected_output_path before verification. This refreshes formula
caches for verification and the browser grid. Use distinct temporary input and
conversion-output paths so LibreOffice never overwrites its own input. Check
the command's exit status and confirm the recalculated file exists. The
conversion command is
libreoffice --headless --convert-to xlsx --outdir <recalc-dir> <temporary.xlsx>;
move its output to expected_output_path.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed 8613c0205249
- 1mo ago First seen · 69 lines · 21 tokens per session scan A 11d186f95ed3
xlsx is a skill published in the GitHub repository MODSetter/SurfSense (16,585 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 825 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
leiloeiro-edital-ranbot-ai
Analise e auditoria de editais de leilao judicial e extrajudicial. Riscos ocultos, clausulas perigosas, debitos, ocupante e classificacao da oportunidade.
officecli-skills
Unified OfficeCLI skill for creating, reading, and editing Office files. Use for any .docx, .pptx, or .xlsx task, including Word documents, PowerPoint decks, Excel workbooks, academic papers, pitch decks, financial models, dashboards, and fillable Word forms. This is the only top-level OfficeCLI skill; route to the…
invoice-organizer
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
first-reader
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta…
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…